(34.234.76.59) 您好!臺灣時間:2019/01/16 20:54
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
本論文永久網址: 
line
研究生:蕭金本
研究生(外文):Bo Hsiao
論文名稱:應用小波轉換於表面瑕疵檢驗
論文名稱(外文):Automatic surface inspection using wavelet transforms
指導教授:蔡篤銘蔡篤銘引用關係
指導教授(外文):Du-Ming Tsai
學位類別:碩士
校院名稱:元智大學
系所名稱:工業工程研究所
學門:工程學門
學類:工業工程學類
論文出版年:1999
畢業學年度:87
語文別:中文
論文頁數:185
中文關鍵詞:瑕疵檢測機器視覺小波轉換多解析多尺度影像還原結構性紋路統計性紋路
外文關鍵詞:Defect inspectionMachine visionWavelet transformMulti-resolutionMulti-scaleStructural textureStatistical texture
相關次數:
  • 被引用被引用:1
  • 點閱點閱:510
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:3
本研究是利用機器視覺的技術來檢測結構性紋路與統計性紋路的表面是否具有瑕疵存在。由於1)小波轉換具有局部性(local)處理的能力,對於小區域之瑕疵能有效凸顯,2)小波具有頻率特性,使得在處理瑕疵上不易受環境影響,3)相對於頻率域之轉換方法,小波轉換處理速度快,因不須事先經過繁複的訓練與數學計算,使得小波轉換在速度處理上有較佳的效率,4)小波轉換不會變動影像物體的相對位置,且保留紋路與瑕疵的空間關係與影像大小,基於上述優點,本研究採用小波轉換技術偵測紋路表面之瑕疵。
傳統上,小波轉換應用於表面瑕疵檢測是擷取小波係數矩陣中紋路特徵值進行處理,由於特徵值選取不易,本研究將採用小波轉換之影像還原技術來檢測表面瑕疵,本研究方法乃利用小波轉換技術之影像轉換與影像還原兩大部份,藉由多尺度、多解析的觀念,配合本研究之還原平滑部份或細節部份之子影像兩策略來凸顯表面瑕疵,同時探討小波基底,還原階數與外在因素對瑕疵檢測之影響,實驗以結構性紋路與統計性紋路(包括布紋、沙紙、皮革、金手指及銑削和刨削工件)為測試樣本,由實驗結果得知紋路中瑕疵皆可有效的被檢測出來。
In this research we aim at automatic surface inspection using wavelet transforms for both structural and statistical textures. Small surface defects generally appear as local anomalies embedded in a homogeneous texture. The nature of the defects leads us toward the multi-scale and multi-resolution analysis method of wavelet transforms, which permits an efficient local spectral analysis.
Wavelet transforms have been traditionally implemented for texture analysis and defect detection by selecting proper textural features in wavelet coefficient matrix. The proposed method does not reply on local texture features. It is based on an image restoration scheme using the wavelet transform. For each wavelet-transformed image, we obtain one smoothed residual sub-image and three detail sub-images, which contain fine structures with horizontal, vertical and diagonal orientation. By properly selecting the smoothed sub-image or detail images for backward wavelet transform, the restored image will remove homogeneous, periodic textures and signify only local anomalies. Experiment on structural textures such as machined surface and textile fabrics, and statistical textures such as sandpaper and leather have shown promising results using the proposed method.
中文摘要…………………………………………………………………………..…V
英文摘要…………………………………………………………………………….V
I誌謝…………………………………………………………………………………VII
目錄………………………………………………………………………………VIII
圖目錄……………………………………..………………………………………XIII
表目錄……………………………..……………………………………………….XIV
第一章 緒論…………………….…………………………………………………….1
1.1 研究動機與目的…………………………………………………………….1
1.2 研究範疇與假設…………………………………………………………….2
1.3 研究方法簡介……………………………………………………………….3
1.4 章節架構…………………………………………………………………….4
第二章 文獻回顧……………………………………………………………………..7
2.1小波轉換應用於影像編碼與圖形辨識……………………………………..7
2.2表面紋路分類與分割………………………………………………………..8
2.3表面瑕疵檢測……………………………………………………………….11
第三章 小波理論……………………………………………………………………14
3.1傅氏窗口轉換 (Window Fourier Transform)………………………………14
3.1.1符號定義…………………..…………………………….…………….14
3.1.2 傅氏窗口函數的時頻分析………………………….……………….15
3.2 小波轉換…………………………………………………………………...17
3.3 小波轉換與還原範例說明…………………………………….…………..20
3.4 小波的多解析影像分析…………………………………….……………..24
3.5 多維小波轉換……………………………………………….……………..26
第四章 研究方法……………………………………………………………………28
4.1 小波濾波器………………………………………………………………...28
4.1.1 正交小波濾波器………………………………………….……...…28
4.1.2 迴旋積………………………………………………………………29
4.1.3 雙正交函數…………………………………………………………30
4.2 小波函數…………………………………………………………………...31
4.2.1小波函數的性質…………………………………………………….37
4.3 小波理論之多解析與多尺度分析…………………………………………43
4.4研究方法流程說明………………………………………………………….51
4.5 程式發展架構………………………………………………………………55
第五章 初步實驗結果…………………...…………………….……………………70
5.1 系統架構與實驗環境…………………………………………….……..…70
5.2 影響檢測結果的因素……………………………………………………...72
5.2.1 基底函數對瑕疵與規則紋路分離結果……………………………72
5.2.2 多尺度階數增加對待測物瑕疵分離情形…………………………91
5.2.3 影像還原策略對凸顯瑕疵的影響………………………………..104
5.2.4 旋轉待測物對檢測結果影響……………………………………..113
5.2.5 瑕疵物體面積大小對小波轉換之檢測影響……………………..127
5.2.6 光源環境對瑕疵檢測之影響……………………………………..132
5.3 傅氏轉換、賈柏轉換與小波轉換……………………………………….144
5.4 小波轉換之工業檢測應用……………………………………………….146
5.5 實驗結果之結論………………………………………………………….154
第六章 結論與建議………………….…………………………………………….157
參考文獻…………………………………………………………………………....160
附錄一 其它正交小波基底之小波係數值………………………………………..165
附錄二 其它雙正交小波基底之小波係數值……………………………………..170
附錄三 其它小波基底四部份之立體圖…………………………………………..173
英文部份
[1] W. E. Stark and W. K. Cheng, "Adaptive coding and modulation for spread spectrum signal", Vehicular Technology Conference, Vol. 3, pp. 1987-1991, 1987.
[2] S. Andrew, "Relationship between spatial frequency selectivity and receptive field profile of simple cells ", J. Physical, Vol. 287 , pp. 163-176,1967.
[3] G. Battle, "A block spin construction of ondeletts Part 1:Lemarie function", Common. Math Phys, Vol. 11, pp. 601-615, 1987.
[4] P. J. Burt and E. H. Adelson, "The Laplacian pyramid as a compact image code", IEEE Trans Common., Vol. COM-31, pp. 532-540, 1983.
[5] F. Campbell, R. Carpenter and J. Levinson,"Visibility of aperiodic patterns compared with cortical cells compared with sinusoidal gratings", J. Physical, Vol. 204 , pp. 283-298, 1969.
[6] I. Daubechies, "Orthonormal bases of compactly supported wavelets", IEEE Trans on Common Pure App. Math, Vol. 41, pp. 909-996, 1988.
[7] D. Gabor, "Theory of Communication", J. Inst. Elec. Eng. , Vol. 93, pp. 429-456, 1946
[8] A. Grossmann, J. Morlet and T. Paul, "Transforms associated to square integral group representations ", Int. J. Math Phys., Vol. 26, pp. 2473-2479, 1986.
[9] A. Grossmann and J. Morlet, "Decomposition of Hardy functions into square integral wavelets of constant shape", SIAM J. Math., Vol. 15, pp.723-736, 1984.
[10] S. Jaffard and Y. Meyer, "Based ondeletts Danes Des overt de rn", J. Math Purees et Appliques,1987.
[11] W. Y. Hung and M. R. Solorzano, "Wavelet preprocessing of acoustic signals", Signal System and Computers, Vol. 12, pp.1114-1118, 1991.
[12] P. G. Lemarie and Y. Meyer, "Ondelette et bases Hibertiennes", Revisit Math lbero Americana, Vol. 2 , 1986.
[13] S. Mallat, "Zero-Crossing of wavelet transform", IEEE Trans. on Information theory, Vol. 37, pp.1019-1023, 1988.
[14] L. Liu and C. R. Meyer, "Optimal contour approximation by deformable piecewise cubic spline", Computer vision and Pattern Recognition, Vol. 1, pp. 638-643, 1991.
[15] S. Mallat, "Multifrequency channel decompositions of image and wavelet models", Acoustic Speech and Signal Processing, Vol. 37, pp. 2091-2110, 1989.
[16] E. Magli, L. Presti and G. Olimo, "A Pattern deletion and compression algorithm based on joint wavelet and random transform", Digital Processing, Vol. 2 , pp. 559-562, 1997.
[17] T. Chang and C.C. Kuo, "Texture analysis and classification with tree-structured wavelet transform", IEEE Trans. Signal Processing, Vol. 1, pp. 429-439, 1993.
[18] B. Robbins, ŖD feature detection via local energy", Elsevier, Vol. 1,pp. 353-368, 1997.
[19] C. S. Lu, "Unsupervised texture segmentation via wavelet transform", Pergamon , Vol. 1 , pp. 729-742, 1997.
[20] T. P. Welon , "Gabor filter design for multiple texture segmentation", Photo Optical Inst. , 1996.
[21] T. Nagai, M. I. Kehare and A. Singh , "A new approach to the design of linear-phase biorthogonal filter banks and wavelet", Signal , System and Computer, Vol. 2, pp. 978-982, 1997.
[22] A. Laine and J. Fan, "Texture classification by wavelet packet signatures", IEEE Pattern Analysis and Machine Intelligence , Vol. 15 , pp.1186-1191, 1993.
[23] O. Pichler , "A Comparison of texture feature extraction using adaptive gabor filter pyramidal and tree structure wavelet transforms", Pergamon , Vol.1 ,pp. 733-742, 1996.
[24] B. E. Shi , "Gabor-Type filtering in space and time with cellular heural network", Circuits and Systems I: Fundamental theory and application, Vol. 45, pp. 121-132, 1998.
[25] D. Dunn ,W. E. Higgins and J. Wakeley , "Texture segmentation using 2D Gabor elementary functions", Pattern analysis and Machine Intelligence , Vol. 16, pp. 130-149, 1994.
[26] S. G. Mallat , "A theory for multi-resolution signal decomposition: The wavelet representation", Circuits and System, Vol.4 , pp. 674-693, 1989.
[27] D. Dunn and W. E. Higgins , "Optimal Gabor filter for texture segmentation", Image Processing , Vol. 14, pp. 947-964.
[28] A. Uhl,"Digital image compression based on non-stationary and inhomogeneous multi-solution analysis", Image Processing , Vol.3 , pp. 365-371, 1996.
[29] A. Bruce and H. Y. Gao, Applied Wavelet Analysis with S-Plus, Springer , New York , 1997.
[30] T. Chang and C. C. Kuo, "A wavelet transform approach to texture analysis", Acoustics Speech and Signal Processing , Vol.4, pp.661-664, 1992.
[31] D. Harwood , "Texture classification by center-symmetric auto-correlation using Kullback discrimination of distribution" , Elservier , 1995
[32] J. Oppenheim and J. Lim , Advanced topics in Signal Processing, Prentice-Hall , N.J , 1988.
[33] J. Stromberg,"A modified franklin system and high-order system of RN as unconditional base for Hard", Spaco in Proc Conf Harmonic Arul, Honor of a Zygmund , Vol. 2 , pp. 475-493.
[34] P. Frederbush, Quantum Field Theory in Ninety Minutes, Math Soc, Bull Amer , 1987.
[35] K. N. Leung, D. A. Bachman, D. A. Herz and D. S. McDonald ,"Positive hydrogen ion beam production by an RF-driven multi-cusp source", Particte Accelerator Conference , Vol. 4 , pp.3 190-3192, 1993.
[36] E. Hall, J.Rang and R.C.Wong ,"Hierarchical search for image matching", Decision Contr. Proc. Conf., Vol. 1 , pp. 791-796, 1976.
[37] D. Marr ,"A theory of human setereo vision", Proc Soc. ,Vol. B204 , pp. 301-328, 1979.
[38] T. Chang and C .C. Kuo, "Texture classification with tree structured wavelet transform", Pattern Recognition, Vol. 2 , pp.256-259, 1992.
[39] G. Loum, P. Provent , J. Lemoine and E. Pettit ,"A new method classification based on wavelet transform", Time-frequency and Time-Scale Analysis, Vol. 1 , pp29-32, 1996.
[40] T. Chang and C. C. Kuo,"A wavelet transform approach to texture analysis", Time-frequency and Time-scale analysis, Vol. 8, pp. 532-593, 1992.
[41] A. L. Amet , A. Ertuzun and E. Ercil , "Texture defect detection using sub-band domain co-occurrence matrix", Image Analysis and Interpretation, Vol. 1, pp. 205-210, 1998.
[42] J. M. Spahiro,"Embedded image coding using zero-tree of wavelet coefficients", Signal Processing, Vol. 41, 1993.
[43] H. S. Sarraf and J.S. Goddard Jr. ,"Robust defect segmentation in woven fabrics", Computer Vision and Pattern Recognition , Vol. 7,pp. 938-944, 1998.
[44] E. Salari and Z. Ling,"Texture Segmentation using hierarchical wavelet transform", Industrial Electronic, Vol. 1, pp. 216-220, 1995.
[45] T. I. Hsu and R. Wilson,"Texture analysis using generalized wavelet transform", Image Processing, Vol. 3, pp. 436-440, 1994.
[46] J. T. Miller and C. C. Li,"Segmentation of object surfaces using the haar wavelet at multiple resolutions", Image Processing , Vol. 3 ,pp. 475-477, 1994.
[47] T. Chang and C. C. Kuo,"A Wavelet Transform approach for hierarchical texture segmentation", Signal System and Computers , Vol. 2 ,pp. 816-820, 1992.
[48] X. P. Zhang and M. D. Desai,"Wavelet based automatic thresholding for image segmentation", Image Processing, Vol. 1, pp. 224-227, 1997.
[49] P. Palisson, N. Zegadi, F. Peynin and R. Unterriener, "Unsupervised multi-resolution texture segmentation using wavelet decomposition" , Image Processing , Vol. 2, pp. 625-629, 1994.
[50] S. Liapis, N. Alvertos and G. Tziritas, "Maximum likelihood texture classification and bayesian texture segmentation using discrete wavelet frames", Digital Signal Processing Proceeding 13th International Conference, Vol. 2 , pp. 1107-1110, 1997.
[51] J. Mao and A. K. Jain ,"Texture classification and segmentation using multi-resolution simultaneous auto-regressive models", Pergamon , Vol.25, pp. 173-188, 1992.
[52] A. V. Nevel,"Texture classification using wavelet frame decompositions", Signal System and Computers, Vol. 1 , pp. 311-314, 1997.
[53] D. Chetverikov, "Texture imperfections ", Pattern Recognition Letter , Vol. 6 , pp. 45-50, 1987.
[54] O. Rioul and P. Duhamel ,"Fast Algorithm for discrete and continuous wavelet transforms", Information Theory , Vol. 38, pp. 569-586, 1992.
[55] T. H. Yu and S. K. Mitra, "Wavelet based hybrid coding scheme" , IEEE International symposium on Circuits and System , Vol. 1 , pp. 377-380, 1997.
[56] A. Fournier, Wavelet and Their Application in Computer Graphics , SIGGRAPH 95 , British Columbia , 1995.
[57] J. R. Paker, Algorithm''s for Image Processing and Computer Vision, John Wiley & Sons Inc, Canada ,1997.
[58] I. Daubechies , Ten Lectures on Wavelets , SIAM,1992.
[59] M. Antonini, M. Barland , P. Mathieu and I. Daubechies ,"Image Coding Using Wavelet Transform", Image Processing, Vol. 1 , 1992.
[60] J. L. Chen and A. Kundu, "Rotation and gray scale transform invariant texture identification using wavelet decomposition and hidden markov model", IEEE Trans. on Pattern Analysis and Machine Intelligence , Vol. 16, pp. 208-214, 1994.
中文部份
[61] 洪金車,張肇建,陳坤元,陳璽煌,"Wavelet Transform for Residudual image compression ",多媒體研討會,高雄,民國84年。
[62] 吳成柯,戴善容,程湘君,雲立實,數位影像處理,民國87年,儒林書局。
[63] 王健亞,"超音波醫學影像分析之研究",成功大學資訊工程研究所碩士論文,民國83年。
[64] 謝嘉俊,"機器視覺在車削金屬表面的瑕疵檢驗之研究",清華大學工業工程研究所碩士論文,民國81年。
[65] 謝志雲,"應用機器視覺於方向性紋路之表面瑕疵檢測",元智大學工業工程研究所碩士論文,民國87年。
[66] 吳松貴,"應用於紋路分析之最佳賈柏過濾器設計",元智大學工業工程研究所碩士論文,民國87年。
[67] 蔡宜壽,林宗華,林正中,"類神經網路於辨識織物瑕疵自動化之應用",技術學刊,12期,171-182頁,民85年。
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔